Lesson 10: Traffic Engineering

Question 1

What is Traffic Engineering

Answer 1

The process of reconfiguring the network in response to changing traffic loads, to achieve some operational goal

Question 2

What are some of the goals a network operator would hope to achieve with Traffic Engineering?

Answer 2

1. Maintain Traffic ratios in a peering relationship
2. Relieve congestion
3. Balance load more evenly across available links in the network

Question 3

What are the questions which Traffic Engineering attempts to answer?

Answer 3

Does the network run efficiently?
How should routing adapt to traffic?
- Avoid congested links
- Satisfy application requirements

Question 4

How can an operator affect how traffic flows in an Intradomain TE topology?

Answer 4

Configure the link weights in one of three ways:

1. Inversely proportionate to capacity
2. Proportional to propagation delay
3. Network-wide optimization

Question 5

What are the three steps to traffic engineering?

Answer 5

1. Measure the network, to determine the current traffic loads
2. Forming a model of how configuration affects the underlying paths in the network
3. Reconfigure the network to exert “control” of how traffic flows

Question 6

The Intradomain traffic engineering problem

Answer 6

Input 1: Graph G(R,L), with R = set of routers, L = set of unidirectional links. Each link L has a fixed capacity, c_L
Input 2: Traffic Matrix M_ij, traffic from Router “i” to router “j”
Output: set of link weights, w_L

Question 7

What si the difference between Intredomain routing and Interdomain routing?

Answer 7

Intradomain: within a domain (e.g. ISP, campus, datacenter)
Interdomain: Between domains

Question 8

Which of the following are examples of interdomain routing?
A: Perring between two ISPs
B: Peering between a university network and its ISP
C: Peering at an internet exchange point (IXP)
D: Routing in a data center:
E: Routing across multiple data centers

Answer 8

A, B, C, & E

Question 9

Interdomain Traffic Engineering

Answer 9

• Alleviate congestion on edge links
• Using new/upgraded edge links
• Changing end-to-end path
• • It involves the reconfiguration of BGP

Question 10

Goals for Interdomain TE

Answer 10

1. Predictability
   
   • No globally visible changes
2. Limit influence of neighbors
   
   • Consistent advertisements, limit AS path
3. Reduce overload of routing changes
   
   • Group prefixes together according to those with common AS paths

Question 11

What is Multipath routing

Answer 11

Where an operator can establish multiple paths in advance. This applies both to Inter and Intradomain routing

Question 12

How can a source router adjust paths?
A. Dropping packets to cause TCP backoff
B. Alternating between multiple forwarding table entries
C. Sending alerts to incoming senders

Answer 12

B

Question 13

What characterizes a data center

Answer 13

1. Multi-tenancy
   
   • allows provider to advertise cost of shared infrastructure
   • Infrastructure must provide security and resource isolation
2. Elastic resources - as traffic expands or contracts, so does the data center usage.
3. Flexible service management - the ability to move work or workloads to other locations inside the datacenter.
   
   • This workload movement, migration is what introduces the need for traffic engineering solutions

Question 14

A key enabling technology in data center networking

Answer 14

The ability to virtualize servers. This enables the quick migration and movement of servers

Question 15

What are the challenges of data center networking?

Answer 15

• Traffic load balance
• Support for virtual machine migration
• Power savings
• Provisioning when demand fluctuates
• Security

Question 16

What are the three layers of the data center topology?

Answer 16

Core (connected to layer-2)
Aggregation (connects access layer)
Access (connects servers)

Question 17

how is the “core” layer of a data center connected?

Answer 17

Historically it used a layer 3 topology, but modern centers are all layer-2 topology.

This makes it easier to do migration of services, so they can stay on the same layer 2 network and would not need new IP addresses.However this makes scaling difficult.

Question 18

What are some problems at the core level of a data center topology?

Answer 18

points of failure

over-subscription - 200x as much traffic as the links at the bottom of the hierarchy

Question 19

How do you address the problem of “scale” with data center “Flat” typologies?

Answer 19

1. Introduce “pods”
   - Each pod has it’s own address
   - Each server has pseudo MAC corresponding to Pod.

Question 20

How do you deal with data centers mapping pseudo MACs to real MAC addresses?

Answer 20

Watch 13.13

Question 21

Where does Jellyfish DC structure constrain expansion
A: Individual servers
B: Aggregation switches
C: Top level switches.

Answer 21

C

Question 22

What is Jellyfish?

Answer 22

A technique to network data centers randomly.
Goals:
High throughput, -> big data
Incremental expanability ->Easy replacement of servers
Problem:
- hypercube : 2k switches
- 3-level fat tree: 5k^2/4 switches

Question 23

What are the two main goals of valiant load balancing?

Answer 23

1 spread traffic evenly across the servers

2. Ensure traffic load is balanced independent of the destinations of the traffic flows